OpenTakeoff runs on your own machine — the client starts it, so there is no endpoint to ping. 2 380 installs a week from npm. Last commit 29 Oct 2026.
Construction takeoff for AI agents: load plans, set scale, measure, count, export with provenance.
What the code does
We read the source, 2 h ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
raw = os.path.join(self.root, "raw", f"{phash}.json")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
Connect this server
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add opentakeoff -- npx -y opentakeoff-mcp{
"mcpServers": {
"opentakeoff": {
"command": "npx",
"args": [
"-y",
"opentakeoff-mcp"
]
}
}
}[mcp_servers.opentakeoff]
command = "npx"
args = ["-y", "opentakeoff-mcp"]{
"mcpServers": {
"opentakeoff": {
"command": "npx",
"args": [
"-y",
"opentakeoff-mcp"
]
}
}
}{
"servers": {
"opentakeoff": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"opentakeoff-mcp"
]
}
}
}Alternatives to OpenTakeoff
same job, measured the same wayConstruction takeoff and estimating for AI agents. Measure a drawing PDF, export a priced estimate.
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Local, explainable knowledge base for AI agents: hybrid search with provenance over SQLite.
Long-term memory for AI agents: local-first PKM with provenance and hybrid search.
Scan what AI agents read for prompt injection: hidden unicode, comment instructions, exfil, lures.
Shared, permission-aware company context for AI agents, with provenance, approvals and audit.
Verifiable provenance for AI agents — ZK proofs over confidential documents, no plaintext exposure.
SEAM: local-first memory runtime for AI agents, with retrieval and glassbox provenance over MCP.
OpenTakeoff — questions
Answers built from our own checks of this server.